EUVIMEDEUVIMED entdecken
Crossref

DBGroup: Dual-Branch Point Grouping for Weakly Supervised 3D Semantic Instance Segmentation

Xuexun Liu, Xiaoxu Xu, Qiudan Zhang, Lin Ma, Xu Wang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (9) · 7341-7349

DOI: 10.1609/aaai.v40i9.37672 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Xuexun Liu und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Weakly supervised 3D instance segmentation is essential for 3D scene understanding, especially as the growing scale of data and high annotation costs associated with fully supervised approaches. Existing methods primarily rely on two forms of weak supervision: one-thing-one-click annotations and bounding box annotations, both of which aim to reduce labeling efforts. However, these approaches still encounter limitations, including labor-intensive annotation processes, high complexity, and reliance on expert annotators. To address these challenges, we propose DBGroup, a two-stage weakly supervised 3D instance segmentation framework that leverages scene-level annotations as a more efficient and scalable alternative. In the first stage, we introduce a Dual-Branch Point Grouping module to generate pseudo labels guided by semantic and mask cues extracted from multi-view images. To further improve label quality, we develop two refinement strategies: Granularity-Aware Instance Merging and Semantic Selection and Propagation. The second stage involves multi-round self-training on an end-to-end instance segmentation network using the refined pseudo-labels. Additionally, we introduce an Instance Mask Filter strategy to address inconsistencies within the pseudo labels. Extensive experiments demonstrate that DBGroup achieves competitive performance compared to sparse-point-level supervised 3D instance segmentation methods, while surpassing state-of-the-art scene-level supervised 3D semantic segmentation approaches.

Zitieren

APA

Liu, X., Xu, X., Zhang, Q., Ma, L., & Wang, X. (2026). DBGroup: Dual-Branch Point Grouping for Weakly Supervised 3D Semantic Instance Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(9), 7341-7349. https://doi.org/10.1609/aaai.v40i9.37672

Vancouver

Liu X, Xu X, Zhang Q, Ma L, Wang X. DBGroup: Dual-Branch Point Grouping for Weakly Supervised 3D Semantic Instance Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(9):7341-7349. doi:10.1609/aaai.v40i9.37672

BibTeX
@article{Liu2026,
  author = {Liu, Xuexun and Xu, Xiaoxu and Zhang, Qiudan and Ma, Lin and Wang, Xu},
  title = {DBGroup: Dual-Branch Point Grouping for Weakly Supervised 3D Semantic Instance Segmentation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {9},
  pages = {7341--7349},
  doi = {10.1609/aaai.v40i9.37672}
}
Kostenlos starten →